Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail
cs.SE, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/openai/codex
Terminology
Sources
- SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
- DaiFu: In-Situ Crash Recovery for Deep Learning Systems
- REDO: Execution-Free Runtime Error Detection for COding Agents
- Towards Agentic Runtime Healing
- CatchAll: Repository-Aware Exception Handling with Knowledge-Guided LLMs
- ProgramBench: Can Language Models Rebuild Programs From Scratch?
- Towards Exception Safety Code Generation with Intermediate Representation Agents Framework
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties